[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MAFB86VRJX0NG1HS4AFE7Y":3,"skill-same:01M6MAFB86VRJX0NG1HS4AFE7Y":85},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6MAFB86VRJX0NG1HS4AFE7Y","miles-rl-training",null,"Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8\u002FINT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fmiles-rl-training\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"training","miles","miles rl training","rl","when","for","production-ready","throughput","Megatron-LM","megatron","slime","alignment","ready","router","use","learning","Transformers","Ray","SGLang","Enterprise","FP8","2026-11-10 10:12:30",false,"---\nname: miles-rl-training\ndescription: Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8\u002FINT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  category: ml-training\n  maintainer: Kalaris Labs\n  tags: Reinforcement Learning, MoE, FP8, INT4, Enterprise, SGLang, Megatron-LM\n  dependencies: sglang-router>=0.2.3, ray, torch>=2.0.0, transformers>=4.40.0\n---\n\n# miles: Enterprise-Grade RL for Large-Scale Model Training\n\nmiles is a high-performance, enterprise-ready RL framework optimized for large-scale model post-training. Built as a production fork of slime, it addresses critical challenges in MoE training stability, low-precision training, and train-inference alignment.\n\n## When to Use miles\n\n**Choose miles when you need:**\n- Training 1TB+ MoE models (DeepSeek V3, Qwen3-MoE)\n- FP8 or INT4 quantization-aware training\n- Bit-wise identical train-inference alignment\n- Speculative RL for maximum throughput\n- Production stability with enterprise support\n\n**Consider alternatives when:**\n- You want the research-grade original → use **slime**\n- You need flexible backend swapping → use **verl**\n- You want PyTorch-native abstractions → use **torchforge**\n\n## Key Features\n\n### Low-Precision Training\n- **Unified FP8**: End-to-end FP8 for both inference and training\n- **INT4 QAT**: 1TB models on single-machine VRAM (H200)\n- **Rollout Routing Replay (R3)**: Bit-wise expert alignment for MoE\n\n### Performance Optimizations\n- **Speculative RL**: 25%+ rollout speedup with online SFT draft models\n- **Zero-Copy Weight Sync**: CUDA IPC zero-copy mapping\n- **Partial Rollout**: Recycle half-finished trajectories\n\n### Train-Inference Alignment\n- **TIS\u002FMIS**: Truncated\u002FMasked Importance Sampling for off-policy correction\n- **Kernel-level optimization**: FlashAttention-3, DeepGEMM integration\n\n## Installation\n\n```bash\n# Recommended: Docker\ndocker pull radixark\u002Fmiles:latest\ndocker run --rm --gpus all --ipc=host --shm-size=16g \\\n  -it radixark\u002Fmiles:latest \u002Fbin\u002Fbash\n\n# From source\ngit clone https:\u002F\u002Fgithub.com\u002Fradixark\u002Fmiles.git\ncd miles\npip install -r requirements.txt\npip install -e .\n```\n\n## Quick Start\n\nmiles inherits slime's configuration system. Basic training:\n\n```bash\npython train.py \\\n    --advantage-estimator grpo \\\n    --model-name qwen3-30b-a3b \\\n    --hf-checkpoint \u002Fpath\u002Fto\u002Fqwen3-30b-a3b-hf \\\n    --rollout-batch-size 512 \\\n    --n-samples-per-prompt 8\n```\n\n---\n\n## Workflow 1: Large MoE Training\n\nUse this workflow for training large MoE models like DeepSeek V3 or Qwen3-MoE.\n\n### Prerequisites Checklist\n- [ ] H100\u002FH200 GPUs with FP8 support\n- [ ] MoE model (DeepSeek V3, Qwen3-MoE)\n- [ ] Docker environment with miles\n\n### Step 1: Environment Setup\n\n```bash\n# FP8 block scaling (recommended for stability)\nexport NVTE_FP8_BLOCK_SCALING_FP32_SCALES=1\nexport CUDA_DEVICE_MAX_CONNECTIONS=1\n```\n\n### Step 2: Configure Training\n\n```bash\npython train.py \\\n    --actor-num-gpus-per-node 8 \\\n    --rollout-num-gpus 8 \\\n    --hf-checkpoint \u002Fpath\u002Fto\u002Fdeepseek-v3 \\\n    --advantage-estimator grpo \\\n    --tensor-model-parallel-size 8 \\\n    --expert-model-parallel-size 4 \\\n    --prompt-data \u002Fpath\u002Fto\u002Fdata.jsonl \\\n    --num-rollout 3000\n```\n\n### Verification Checklist\n- [ ] Model loads without errors\n- [ ] Routing decisions are consistent\n- [ ] No NaN\u002FInf in loss values\n\n---\n\n## Workflow 2: Speculative RL Training\n\nUse this workflow for maximum rollout throughput with EAGLE speculative decoding.\n\n### How Speculative RL Works\n\n1. Small draft model generates candidate tokens\n2. Target model verifies in parallel\n3. Draft model updated via online SFT to track policy\n\n### Step 1: Enable Speculative Decoding\n\nmiles supports EAGLE speculative decoding via SGLang:\n\n```bash\npython train.py \\\n    --actor-num-gpus-per-node 8 \\\n    --hf-checkpoint \u002Fpath\u002Fto\u002Ftarget-model \\\n    --sglang-speculative-algorithm EAGLE \\\n    --sglang-speculative-num-steps 3 \\\n    --sglang-speculative-eagle-topk 1 \\\n    --sglang-speculative-num-draft-tokens 4 \\\n    --sglang-speculative-draft-model-path \u002Fpath\u002Fto\u002Fdraft-model \\\n    --advantage-estimator grpo \\\n    --prompt-data \u002Fpath\u002Fto\u002Fdata.jsonl\n```\n\n### Step 2: Enable Online MTP Training (Optional)\n\nFor online SFT of draft model during training:\n\n```bash\n--mtp-num-layers 1 \\\n--enable-mtp-training \\\n--mtp-loss-scaling-factor 0.2\n```\n\n**Note**: Online MTP training requires a torch dist checkpoint with MTP weights. Add `--mtp-num-layers 1` during checkpoint conversion from HuggingFace.\n\n### Expected Speedup\n\n- **Standard rollout**: Baseline\n- **Speculative RL**: 25-40% faster rollout\n- **With partial rollout**: Additional 10-15% throughput\n\n---\n\n## Configuration Reference\n\nmiles inherits all slime arguments. See slime API Reference for the complete list.\n\n### Cluster Resources (from slime)\n\n```bash\n--actor-num-nodes 1\n--actor-num-gpus-per-node 8\n--rollout-num-gpus 8\n--rollout-num-gpus-per-engine 2\n--colocate\n```\n\n### Megatron Parallelism (from slime)\n\n```bash\n--tensor-model-parallel-size 8\n--pipeline-model-parallel-size 2\n--expert-model-parallel-size 4    # MoE expert parallelism\n```\n\n### Speculative Decoding (miles-specific)\n\n```bash\n--sglang-speculative-algorithm EAGLE\n--sglang-speculative-num-steps 3\n--sglang-speculative-eagle-topk 1\n--sglang-speculative-num-draft-tokens 4\n--sglang-enable-draft-weights-cpu-backup\n--sglang-speculative-draft-model-path \u002Fyour\u002Fdraft\u002Fmodel\u002Fpath\n```\n\n### Online MTP Training (miles-specific)\n\n```bash\n--mtp-num-layers 1\n--enable-mtp-training\n--mtp-loss-scaling-factor 0.2\n```\n\n---\n\n## Key Features (Conceptual)\n\nThe following features are documented in miles but specific CLI flags may vary. Consult the miles repository for latest configuration.\n\n### Unified FP8 Pipeline\n\nEnd-to-end FP8 sampling and training that eliminates quantization-induced discrepancy causing RL collapse in MoE models.\n\n### Rollout Routing Replay (R3)\n\nRecords expert routing decisions during SGLang inference and replays them during Megatron training for bit-wise expert alignment.\n\n**How R3 Works**:\n1. During SGLang inference, expert routing decisions are recorded\n2. Routing decisions stored in `sample.rollout_routed_experts`\n3. During Megatron training, routing is replayed instead of recomputed\n4. Ensures identical expert selection between train and inference\n\n### INT4 Quantization-Aware Training\n\nEnables single-machine deployment of 1TB+ models (e.g., on H200).\n\n**Memory Savings with INT4**:\n\n| Model Size | BF16 VRAM | INT4 VRAM | Reduction |\n|------------|-----------|-----------|-----------|\n| 70B | 140GB | 45GB | 3.1x |\n| 235B | 470GB | 150GB | 3.1x |\n| 671B | 1.3TB | 420GB | 3.1x |\n\n### Train-Inference Alignment\n\nmiles achieves \"exactly 0 KL divergence\" between training and inference through:\n- Flash Attention 3\n- DeepGEMM\n- Batch-invariant kernels from Thinking Machines Lab\n- `torch.compile` integration\n\n---\n\n## Sample Data Structure\n\nmiles uses the same `Sample` dataclass as slime with the `rollout_routed_experts` field for MoE routing replay:\n\n```python\n@dataclass\nclass Sample:\n    prompt: str | list[dict]\n    tokens: list[int]\n    response: str\n    reward: float | dict\n    loss_mask: list[int]\n    status: Status\n    metadata: dict\n    rollout_log_probs: list[float]\n    rollout_routed_experts: list[list[int]]  # MoE routing for R3\n```\n\nSee slime API Reference for the complete Sample definition.\n\n---\n\n## Common Issues and Solutions\n\n### Issue: FP8 Training Collapse\n\n**Symptoms**: Loss explodes, NaN values\n\n**Solutions**:\n- Use block scaling: `export NVTE_FP8_BLOCK_SCALING_FP32_SCALES=1`\n- Reduce learning rate: `--lr 5e-7`\n- Ensure MoE routing is consistent between train\u002Finference\n\n### Issue: Speculative Draft Drift\n\n**Symptoms**: Low acceptance rate over time\n\n**Solutions**:\n- Enable online MTP training to keep draft model aligned\n- Reduce speculative steps: `--sglang-speculative-num-steps 2`\n- Use CPU backup: `--sglang-enable-draft-weights-cpu-backup`\n\n### Issue: Train-Inference Mismatch\n\n**Symptoms**: Policy divergence, reward collapse\n\n**Solutions**:\n- Use TIS for off-policy correction: `--use-tis --tis-threshold 0.9`\n- Verify log probs match between SGLang and Megatron\n- Enable R3 for MoE models\n\n---\n\n## Supported Models\n\n| Family | Models | MoE Support |\n|--------|--------|-------------|\n| DeepSeek | R1, V3, V3.2 | Full |\n| Qwen | 2, 2.5, 3 (including MoE) | Full |\n| Llama | 3, 3.1, 3.3, 4 | Dense only |\n| Gemma | 2, 3, 3N | Dense only |\n| GLM | 4.5, 4.6, 4.7 | Dense only |\n| MiniMax | M2, M2.1 | Full |\n\n---\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fradixark\u002Fmiles\n- **Introduction Blog**: https:\u002F\u002Flmsys.org\u002Fblog\u002F2025-11-19-miles\u002F\n- **Slime (upstream)**: https:\u002F\u002Fgithub.com\u002FTHUDM\u002Fslime\n- **SGLang**: https:\u002F\u002Fgithub.com\u002Fsgl-project\u002Fsglang\n\n## Related skills\n\n- `tensorrt-llm`: Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency.\n- `slime-rl-training`: Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework.\n- `serving-llms-vllm`: Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.\n","# miles: Enterprise-Grade RL for Large-Scale Model Training\n\nmiles is a high-performance, enterprise-ready RL framework optimized for large-scale model post-training. Built as a production fork of slime, it addresses critical challenges in MoE training stability, low-precision training, and train-inference alignment.\n\n## When to Use miles\n\n**Choose miles when you need:**\n- Training 1TB+ MoE models (DeepSeek V3, Qwen3-MoE)\n- FP8 or INT4 quantization-aware training\n- Bit-wise identical train-inference alignment\n- Speculative RL for maximum throughput\n- Production stability with enterprise support\n\n**Consider alternatives when:**\n- You want the research-grade original → use **slime**\n- You need flexible backend swapping → use **verl**\n- You want PyTorch-native abstractions → use **torchforge**\n\n## Key Features\n\n### Low-Precision Training\n- **Unified FP8**: End-to-end FP8 for both inference and training\n- **INT4 QAT**: 1TB models on single-machine VRAM (H200)\n- **Rollout Routing Replay (R3)**: Bit-wise expert alignment for MoE\n\n### Performance Optimizations\n- **Speculative RL**: 25%+ rollout speedup with online SFT draft models\n- **Zero-Copy Weight Sync**: CUDA IPC zero-copy mapping\n- **Partial Rollout**: Recycle half-finished trajectories\n\n### Train-Inference Alignment\n- **TIS\u002FMIS**: Truncated\u002FMasked Importance Sampling for off-policy correction\n- **Kernel-level optimization**: FlashAttention-3, DeepGEMM integration\n\n## Installation\n\n```bash\n# Recommended: Docker\ndocker pull radixark\u002Fmiles:latest\ndocker run --rm --gpus all --ipc=host --shm-size=16g \\\n  -it radixark\u002Fmiles:latest \u002Fbin\u002Fbash\n\n# From source\ngit clone https:\u002F\u002Fgithub.com\u002Fradixark\u002Fmiles.git\ncd miles\npip install -r requirements.txt\npip install -e .\n```\n\n## Quick Start\n\nmiles inherits slime's configuration system. Basic training:\n\n```bash\npython train.py \\\n    --advantage-estimator grpo \\\n    --model-name qwen3-30b-a3b \\\n    --hf-checkpoint \u002Fpath\u002Fto\u002Fqwen3-30b-a3b-hf \\\n    --rollout-batch-size 512 \\\n    --n-samples-per-prompt 8\n```\n\n---\n\n## Workflow 1: Large MoE Training\n\nUse this workflow for training large MoE models like DeepSeek V3 or Qwen3-MoE.\n\n### Prerequisites Checklist\n- [ ] H100\u002FH200 GPUs with FP8 support\n- [ ] MoE model (DeepSeek V3, Qwen3-MoE)\n- [ ] Docker environment with miles\n\n### Step 1: Environment Setup\n\n```bash\n# FP8 block scaling (recommended for stability)\nexport NVTE_FP8_BLOCK_SCALING_FP32_SCALES=1\nexport CUDA_DEVICE_MAX_CONNECTIONS=1\n```\n\n### Step 2: Configure Training\n\n```bash\npython train.py \\\n    --actor-num-gpus-per-node 8 \\\n    --rollout-num-gpus 8 \\\n    --hf-checkpoint \u002Fpath\u002Fto\u002Fdeepseek-v3 \\\n    --advantage-estimator grpo \\\n    --tensor-model-parallel-size 8 \\\n    --expert-model-parallel-size 4 \\\n    --prompt-data \u002Fpath\u002Fto\u002Fdata.jsonl \\\n    --num-rollout 3000\n```\n\n### Verification Checklist\n- [ ] Model loads without errors\n- [ ] Routing decisions are consistent\n- [ ] No NaN\u002FInf in loss values\n\n---\n\n## Workflow 2: Speculative RL Training\n\nUse this workflow for maximum rollout throughput with EAGLE speculative decoding.\n\n### How Speculative RL Works\n\n1. Small draft model generates candidate tokens\n2. Target model verifies in parallel\n3. Draft model updated via online SFT to track policy\n\n### Step 1: Enable Speculative Decoding\n\nmiles supports EAGLE speculative decoding via SGLang:\n\n```bash\npython train.py \\\n    --actor-num-gpus-per-node 8 \\\n    --hf-checkpoint \u002Fpath\u002Fto\u002Ftarget-model \\\n    --sglang-speculative-algorithm EAGLE \\\n    --sglang-speculative-num-steps 3 \\\n    --sglang-speculative-eagle-topk 1 \\\n    --sglang-speculative-num-draft-tokens 4 \\\n    --sglang-speculative-draft-model-path \u002Fpath\u002Fto\u002Fdraft-model \\\n    --advantage-estimator grpo \\\n    --prompt-data \u002Fpath\u002Fto\u002Fdata.jsonl\n```\n\n### Step 2: Enable Online MTP Training (Optional)\n\nFor online SFT of draft model during training:\n\n```bash\n--mtp-num-layers 1 \\\n--enable-mtp-training \\\n--mtp-loss-scaling-factor 0.2\n```\n\n**Note**: Online MTP training requires a torch dist checkpoint with MTP weights. Add `--mtp-num-layers 1` during checkpoint conversion from HuggingFace.\n\n### Expected Speedup\n\n- **Standard rollout**: Baseline\n- **Speculative RL**: 25-40% faster rollout\n- **With partial rollout**: Additional 10-15% throughput\n\n---\n\n## Configuration Reference\n\nmiles inherits all slime arguments. See slime API Reference for the complete list.\n\n### Cluster Resources (from slime)\n\n```bash\n--actor-num-nodes 1\n--actor-num-gpus-per-node 8\n--rollout-num-gpus 8\n--rollout-num-gpus-per-engine 2\n--colocate\n```\n\n### Megatron Parallelism (from slime)\n\n```bash\n--tensor-model-parallel-size 8\n--pipeline-model-parallel-size 2\n--expert-model-parallel-size 4    # MoE expert parallelism\n```\n\n### Speculative Decoding (miles-specific)\n\n```bash\n--sglang-speculative-algorithm EAGLE\n--sglang-speculative-num-steps 3\n--sglang-speculative-eagle-topk 1\n--sglang-speculative-num-draft-tokens 4\n--sglang-enable-draft-weights-cpu-backup\n--sglang-speculative-draft-model-path \u002Fyour\u002Fdraft\u002Fmodel\u002Fpath\n```\n\n### Online MTP Training (miles-specific)\n\n```bash\n--mtp-num-layers 1\n--enable-mtp-training\n--mtp-loss-scaling-factor 0.2\n```\n\n---\n\n## Key Features (Conceptual)\n\nThe following features are documented in miles but specific CLI flags may vary. Consult the miles repository for latest configuration.\n\n### Unified FP8 Pipeline\n\nEnd-to-end FP8 sampling and training that eliminates quantization-induced discrepancy causing RL collapse in MoE models.\n\n### Rollout Routing Replay (R3)\n\nRecords expert routing decisions during SGLang inference and replays them during Megatron training for bit-wise expert alignment.\n\n**How R3 Works**:\n1. During SGLang inference, expert routing decisions are recorded\n2. Routing decisions stored in `sample.rollout_routed_experts`\n3. During Megatron training, routing is replayed instead of recomputed\n4. Ensures identical expert selection between train and inference\n\n### INT4 Quantization-Aware Training\n\nEnables single-machine deployment of 1TB+ models (e.g., on H200).\n\n**Memory Savings with INT4**:\n\n| Model Size | BF16 VRAM | INT4 VRAM | Reduction |\n|------------|-----------|-----------|-----------|\n| 70B | 140GB | 45GB | 3.1x |\n| 235B | 470GB | 150GB | 3.1x |\n| 671B | 1.3TB | 420GB | 3.1x |\n\n### Train-Inference Alignment\n\nmiles achieves \"exactly 0 KL divergence\" between training and inference through:\n- Flash Attention 3\n- DeepGEMM\n- Batch-invariant kernels from Thinking Machines Lab\n- `torch.compile` integration\n\n---\n\n## Sample Data Structure\n\nmiles uses the same `Sample` dataclass as slime with the `rollout_routed_experts` field for MoE routing replay:\n\n```python\n@dataclass\nclass Sample:\n    prompt: str | list[dict]\n    tokens: list[int]\n    response: str\n    reward: float | dict\n    loss_mask: list[int]\n    status: Status\n    metadata: dict\n    rollout_log_probs: list[float]\n    rollout_routed_experts: list[list[int]]  # MoE routing for R3\n```\n\nSee slime API Reference for the complete Sample definition.\n\n---\n\n## Common Issues and Solutions\n\n### Issue: FP8 Training Collapse\n\n**Symptoms**: Loss explodes, NaN values\n\n**Solutions**:\n- Use block scaling: `export NVTE_FP8_BLOCK_SCALING_FP32_SCALES=1`\n- Reduce learning rate: `--lr 5e-7`\n- Ensure MoE routing is consistent between train\u002Finference\n\n### Issue: Speculative Draft Drift\n\n**Symptoms**: Low acceptance rate over time\n\n**Solutions**:\n- Enable online MTP training to keep draft model aligned\n- Reduce speculative steps: `--sglang-speculative-num-steps 2`\n- Use CPU backup: `--sglang-enable-draft-weights-cpu-backup`\n\n### Issue: Train-Inference Mismatch\n\n**Symptoms**: Policy divergence, reward collapse\n\n**Solutions**:\n- Use TIS for off-policy correction: `--use-tis --tis-threshold 0.9`\n- Verify log probs match between SGLang and Megatron\n- Enable R3 for MoE models\n\n---\n\n## Supported Models\n\n| Family | Models | MoE Support |\n|--------|--------|-------------|\n| DeepSeek | R1, V3, V3.2 | Full |\n| Qwen | 2, 2.5, 3 (including MoE) | Full |\n| Llama | 3, 3.1, 3.3, 4 | Dense only |\n| Gemma | 2, 3, 3N | Dense only |\n| GLM | 4.5, 4.6, 4.7 | Dense only |\n| MiniMax | M2, M2.1 | Full |\n\n---\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fradixark\u002Fmiles\n- **Introduction Blog**: https:\u002F\u002Flmsys.org\u002Fblog\u002F2025-11-19-miles\u002F\n- **Slime (upstream)**: https:\u002F\u002Fgithub.com\u002FTHUDM\u002Fslime\n- **SGLang**: https:\u002F\u002Fgithub.com\u002Fsgl-project\u002Fsglang\n\n## Related skills\n\n- `tensorrt-llm`: Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency.\n- `slime-rl-training`: Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework.\n- `serving-llms-vllm`: Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.\n",{"name":5,"license":15,"metadata":45,"description":7},{"tags":46,"version":47,"category":48,"maintainer":49,"dependencies":50},"Reinforcement Learning, MoE, FP8, INT4, Enterprise, SGLang, Megatron-LM","1.0.0","ml-training","Kalaris Labs","sglang-router>=0.2.3, ray, torch>=2.0.0, transformers>=4.40.0","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fmiles-rl-training",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill miles-rl-training",{"tool":67,"command":68},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill miles-rl-training",{"tool":70,"command":71},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill miles-rl-training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fmiles-rl-training\u002FSKILL.md",true,[75,81],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fapi-reference.md","REFERENCE","参考文档",4094,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fmiles-rl-training\u002Freferences\u002Fapi-reference.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Ftroubleshooting.md",5814,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fmiles-rl-training\u002Freferences\u002Ftroubleshooting.md",[86,95,103,111,119,127],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":94},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":94},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":94},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":94},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":94},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":131,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":94},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]